Training in progress, step 2480, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58df8933593be515378f4ed26531652372f20b456ad4d4f899eb46e2ffc95ce1
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c9904e7e622e8f841d2638f3478e33d1225746b6513ebf98cba149ef2ca639
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c0f664a3363567917c69321a2cc9180a5dc58a60087edf86b1fb088a0865651
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d3a91cf25ce58560d2917160a1aaffcee398f1ff65559c5d58abcd7610b9f59
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2488,6 +2488,16 @@
|
|
| 2488 |
"mean_token_accuracy": 0.7648072987794876,
|
| 2489 |
"num_tokens": 11484816.0,
|
| 2490 |
"step": 2470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2491 |
}
|
| 2492 |
],
|
| 2493 |
"logging_steps": 10,
|
|
@@ -2507,7 +2517,7 @@
|
|
| 2507 |
"attributes": {}
|
| 2508 |
}
|
| 2509 |
},
|
| 2510 |
-
"total_flos": 5.
|
| 2511 |
"train_batch_size": 4,
|
| 2512 |
"trial_name": null,
|
| 2513 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5290666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2488 |
"mean_token_accuracy": 0.7648072987794876,
|
| 2489 |
"num_tokens": 11484816.0,
|
| 2490 |
"step": 2470
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"entropy": 0.9790533006191253,
|
| 2494 |
+
"epoch": 0.5290666666666667,
|
| 2495 |
+
"grad_norm": 0.2507703900337219,
|
| 2496 |
+
"learning_rate": 8.643942596826911e-05,
|
| 2497 |
+
"loss": 1.1305276870727539,
|
| 2498 |
+
"mean_token_accuracy": 0.7577844798564911,
|
| 2499 |
+
"num_tokens": 11526756.0,
|
| 2500 |
+
"step": 2480
|
| 2501 |
}
|
| 2502 |
],
|
| 2503 |
"logging_steps": 10,
|
|
|
|
| 2517 |
"attributes": {}
|
| 2518 |
}
|
| 2519 |
},
|
| 2520 |
+
"total_flos": 5.468820962062848e+16,
|
| 2521 |
"train_batch_size": 4,
|
| 2522 |
"trial_name": null,
|
| 2523 |
"trial_params": null
|